JP7034730B2 - Devices, methods, and programs for setting information related to scanned images - Google Patents

Description

The present invention relates to a technique for setting information related to a scanned image obtained by scanning.

Conventionally, image data obtained by scanning a paper document (hereinafter referred to as scanned image data) is subjected to character recognition processing (hereinafter referred to as OCR processing), and the recognized characters are used as an electronic file of the paper document. There is a technique to use as a file name.

Patent Document 1 discloses a technique of performing OCR processing on a predetermined place in the scanned image data of a form and creating a file using the obtained characters as a file name.

Japanese Unexamined Patent Publication No. 62-051866

In the form that is a paper document, in addition to the format in which the position of the items to be described and the size of the entry column (entry area) are predetermined, the position of the items to be described is not predetermined and is in the same format. However, the description column can be expanded, and the position of the description item may change depending on the size. For example, a quotation, which is a type of form, includes a table in which the description area expands downward according to the type of product, and a form containing items whose description position changes according to the size of the description area in the table. be. In Patent Document 1, the place (region) where the OCR processing is performed is predetermined. OCR processing is performed on the specified location using the scanned image data of the estimate that the position of the items to be described is not determined in advance and changes according to the size of the entry field, and a file with the obtained characters as the file name is created. Then, there is a possibility that the file name contains unintended characters. That is, there is a possibility that the area where the OCR processing is performed cannot be properly specified. In addition, not limited to forms, if the position of the items to be described is not determined in advance and the document changes according to the size of the entry column, the area to be OCR processed is appropriately specified. There was a possibility that it could not be done.

The present invention has been made in view of the above problems, and in a scene where a file name or the like is set using a character string obtained by performing OCR processing on a scanned image, an area for performing OCR processing is provided. It is intended to be properly identified.

The device according to one aspect of the present invention is a device for setting information in the scanned image data obtained by scanning a document including a table, and is presumed to be a character string and a table in the new scanned image data. The area information extracted from each of the character string area and the table area , the area information extracted by the extraction means in the new scanned image data, and the past scanned image data respectively. By comparing with the area information, the determination means for determining the past scan image data from which the area information similar to the area information extracted in the new scan image data is extracted, and the similar area information The character string area used when setting information for the past scanned image data determined to have been extracted by the determination means, and the past determined by the determination means that similar area information has been extracted . A detection means for detecting a target area to be processed among the character string areas extracted from the new scan image data based on the distance between the table area extracted in the scanned image data, and the above-mentioned detection means. It is characterized by having a recognition means for performing character recognition processing in a target area and a setting means for setting information in the new scanned image data using characters obtained as a result of the character recognition processing .

According to the present invention, it is possible to appropriately specify an area to be OCR processed in a scene where a file name or the like is set using a character string obtained by performing OCR processing on a scanned image.

It is a figure which shows the whole structure of an image processing system. It is a hardware block diagram of the MFP. It is a hardware configuration diagram of a file server. It is a software block diagram of the MFP. It is a flowchart which shows the flow of the whole control until the character string area information is saved. It is a figure which shows an example of a scan setting screen. It is a flowchart which shows the flow of image processing. It is a figure which shows an example of the document to be scanned and the preview screen. It is a flowchart which shows the details of a file name generation process. It is a figure which shows an example of the upload setting screen. It is a flowchart which derives a character string area using a file name. It is a figure which shows the document to be scanned and another example of a preview screen. It is a flowchart which derives the file name use character string area of Embodiment 2. It is a flowchart which shows the detail of the distance derivation process. It is a figure which shows the document to be scanned and another example of a preview screen. It is a figure which shows an example of the file name list display.

Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. It should be noted that the following embodiments do not limit the invention according to the claims, and not all combinations of features described in the embodiments are essential for the means for solving the invention.

[Embodiment 1]
<Configuration of image processing system>
FIG. 1 is a diagram showing an overall configuration of an image processing system according to the present embodiment. The image processing system is composed of an MFP 110 and a file server 120, and is communicably connected to each other via a LAN (Local Area Network).

The MFP (Multi Function Printer) 110 is a multifunction device having a plurality of functions such as a scanner and a printer, and is an example of an image processing device. The file server 120 is an example of an external server that stores and manages an electronic document file. The image processing system of the present embodiment is configured to include the MFP 110 and the file server 120, but is not limited thereto. For example, the MFP 110 may also serve as the file server 120. Further, instead of LAN, a connection form via the Internet or the like may be used. Further, the MFP 110 is connected to a PSTN (Public Switched Telephone Network) and can perform facsimile communication of image data with a facsimile machine (not shown).

<Hardware configuration of MFP>
FIG. 2 is a hardware configuration diagram of the MFP 110. The MFP 110 is composed of a control unit 210, an operation unit 220, a printer unit 221, a scanner unit 222, and a modem 223. The control unit 210 is composed of the following units 211 to 219, and controls the operation of the entire MFP 110. The CPU 211 reads out the control program stored in the ROM 212 and executes / controls various functions of the MFP 110 such as reading / printing / communication. The RAM 213 is used as a temporary storage area for the main memory, work area, etc. of the CPU 211. In this embodiment, one CPU 211 uses one memory (RAM 213 or HDD 214) to perform each process shown in the flowchart described later, but other embodiments may be used. For example, a plurality of CPUs, a plurality of RAMs, or HDDs may be linked to perform each process. HDD 214 is a large-capacity storage unit that stores image data and various programs. The operation unit I / F 215 is an interface for connecting the operation unit 220 and the control unit 210. The operation unit 220 is provided with a liquid crystal display unit having a touch panel function, a keyboard, and the like, and serves as a reception unit for receiving operations / inputs / instructions by the user. These operations by the user may be accepted by touching the liquid crystal panel, or may be accepted by the operation of the keyboard, buttons, or the like by the user. The printer unit I / F 216 is an interface for connecting the printer unit 221 and the control unit 210. The image data for printing is transferred from the control unit 210 to the printer unit 221 via the printer unit I / F 216 and printed on the recording medium. The scanner unit I / F217 is an interface for connecting the scanner unit 222 and the control unit 210. The scanner unit 222 reads a document set in a document table (not shown) or an ADF (Auto Document Feeder) to generate image data, and inputs the image data to the control unit 210 via the scanner unit I / F 217. The MFP 110 can print out (copy) the image data generated by the scanner unit 222 from the printer unit 221, and can also send a file or send an e-mail. The modem I / F 218 is an interface for connecting the modem 223 and the control unit 210. Modem 223 facsimiles and communicates image data with a facsimile machine on the PSTN. The network I / F 219 is an interface for connecting the control unit 210 (MFP110) to the LAN. The MFP 110 uses the network I / F 219 to transmit image data and information to an external device (file server 120, etc.) on the LAN, and to receive various information.

<Hardware configuration of file server>
FIG. 3 is a hardware configuration diagram of the file server 120. The file server 120 is composed of a CPU 311, a ROM 312, a RAM 313, an HDD 314, and a network I / F 315. The CPU 311 reads the control program stored in the ROM 312 and performs various processes to control the operation of the entire file server 120. The RAM 313 is used as a temporary storage area such as a main memory and a work area of the CPU 311. The HDD 314 is a large-capacity storage unit that stores image data and various programs. The network I / F315 is an interface for connecting the file server 120 to the LAN. The file server 120 uses the network I / F315 to send and receive various information to and from other devices (for example, MFP110) on the LAN.

<Software configuration of MFP>
FIG. 4 is a diagram showing an example of the software configuration of the MFP 110. The MFP 110 has a native function module 410 and an additional function module 420. Each part included in the native function module 410 is provided as standard in the MFP 110, while each part of the additional function module 420 is an application additionally installed in the MFP 110. The additional function module 420 is an application based on Java (registered trademark), and can easily realize the addition of functions to the MFP 110. In addition, other additional function modules (additional applications) (not shown) may be installed in the MFP 110.

The native function module 410 has a scan execution unit 411 and an image data storage unit 412. The additional function module 420 has a scan instruction unit 421, a metadata generation unit 422, an image analysis unit 423, an upload execution unit 424, a file generation unit 425, a display control unit 426, and a form information holding unit 427.

The display control unit 426 displays a UI (user interface) screen for receiving operations, inputs, instructions, and the like by the user on the liquid crystal display unit having the touch panel function of the operation unit 220 of the MFP 110. The details of the UI screen to be displayed will be described later.

The scan instruction unit 421 requests the scan execution unit 411 to perform a scan process together with the scan setting and transfer setting information included in the user instruction according to the user instruction input via the display control unit 426.

The scan execution unit 411 receives a scan request including scan settings from the scan instruction unit 421. The scan execution unit 411 generates scan image data by scanning an image on a document with the scanner unit 222 via the scanner unit I / F 217. The scan execution unit 411 sends the generated scan image data to the image data storage unit 412. At this time, the scan execution unit 411 sends a scan image identifier uniquely indicating the saved scan image data to the scan instruction unit 421.

The image data storage unit 412 stores the scanned image data received from the scan execution unit 411 in the HDD 214.

The scan instruction unit 421 acquires the scan image data corresponding to the scan image identifier received from the scan execution unit 411 from the image data storage unit 412. The scan instruction unit 421 requests the metadata generation unit 422 to generate metadata of the acquired scan image data. The metadata is information related to the scanned image data, and examples thereof include a file name given to the scanned image data. Hereinafter, in the present embodiment, the case where the metadata is a file name will be described as an example.

The metadata generation unit 422 sends an analysis instruction of the scanned image data to the image analysis unit 423. The image analysis unit 423 performs image analysis (layout analysis processing and OCR processing (character string recognition processing)) on the scanned image data based on the analysis instruction from the metadata generation unit 422. The image analysis unit 423 sends the area information obtained by image analysis of the scanned image data to the metadata generation unit 422 as an analysis result. Table 1 shows an example of area information. The area information includes a number for identifying the area, an X coordinate, a Y coordinate, a width, and a height of the area, and a type of the area for each area such as a character string area and a table area included in the scanned image data. Contains information to indicate. Here, the character string area is an area in which text is detected by image analysis, and the table area is an area in which a table is detected by image analysis. Since the method of detecting texts and tables from image data is widely known, the description thereof will be omitted. Further, in Table 1, for the sake of simplicity, only a part of the area in the scanned image data is shown.

The image analysis unit 423 compares the area information obtained by the current image analysis with each of the area information obtained by the previous (past) image analysis. The area information obtained in the previous image analysis is held by the form information holding unit 427. Further, to each area information held by the form information holding unit 427, selection information for specifying a character string area selected by the user as a file name in the file name generation process of step S508 described later is added. Hereinafter, the information obtained by adding the selection information to the area information is referred to as form information. When the image analysis unit 423 determines that the form information holding unit 427 holds the area information similar to the area information obtained in the current image analysis by the above comparison, the image analysis unit 423 further determines that the similar area information (hereinafter referred to as "the area information"). It is determined whether the selection information is added to (referred to as similar area information). When it is determined that the selection information is added to the similar area information, the image analysis unit 423 obtains the selection information and the character string area (hereinafter referred to as the selection character area) indicated by the selection information by OCR processing. The character string is included in the analysis result of the image analysis and sent to the metadata generation unit 422. Details will be described later. The analysis result of the image analysis is also sent to the display control unit 426 via the metadata generation unit 422.

Further, the metadata generation unit 422 generates metadata (file name in the present embodiment) based on the user instruction input via the UI screen and the analysis result of the image analysis unit 423. The metadata generation unit 422 sends the scanned image identifier and the generated metadata to the upload execution unit 424. Then, the metadata generation unit 422 instructs the upload execution unit 424 to upload the scanned image data to the file server 120.

Further, the metadata generation unit 422 sends a display instruction to the display control unit 426. The display control unit 426 displays a UI screen (for example, FIG. 8B) on the liquid crystal display unit having the touch panel function of the operation unit 220 of the MFP 110 based on the display instruction from the metadata generation unit 422. The UI screen is a screen for receiving operations, inputs, and instructions for generating a file name. Further, the display control unit 426 displays the preview image of the scanned image data on the UI screen based on the display instruction from the metadata generation unit 422.

The upload execution unit 424 sends a display instruction of the UI screen to the display control unit 426. The display control unit 426 displays a UI screen (for example, FIG. 10) for accepting a folder path setting and upload operation, input, and instruction from the user. The details of the UI screen displayed at this time will be described later. Further, the upload execution unit 424 receives an upload instruction from the user, and instruct the file generation unit 425 to generate a file of the scan image data indicated by the scan image identifier according to the instruction.

The file generation unit 425 acquires the scan image data corresponding to the instructed scan image identifier from the image data storage unit 412, and generates a file to be transmitted to the file server 120.

The upload execution unit 424 connects to the file server 120 using the set folder path setting and the file name generated by the metadata generation unit 422, and transmits the file generated by the file generation unit 425. When the upload is completed, the upload execution unit 424 notifies the display control unit 426 that the upload is completed. The display control unit 426 receives a notification from the upload execution unit 424 and updates the display content. The upload execution unit 424 has an SMB (Server Message Block) client function. As a result, file and folder operations are performed using the SMB on the file server 120 having the SMB server function. In addition to SMB, WebDAV (Distributed Photography and Versioning protocol for the WWW) can be used. Further, FTP (File Transfer Protocol), SMTP (Simple Mail Transfer Protocol) and the like can also be used. In addition, SOAP, REST (Representational State Transfer), and the like other than those for the purpose of file transmission can also be used.

<Flow chart of the whole process>
FIG. 5 is a flowchart showing the overall control flow up to the storage of the character string area information. This series of processing is realized by the CPU 211 of the MFP 110 executing the control program stored in the HDD 214. Hereinafter, it will be described in detail.

Here, a series of processes up to the storage of the character string area information will be described for two similar documents based on the flowchart of FIG. In the first implementation, a case where the form information holding unit 427 does not hold any form information (information of similar documents) and performs a series of processing on one of the documents will be described.

Subsequently, in the second implementation, the form information of the document to be scanned in the first implementation is held by the form information holding unit 427, and the other document similar to the document to be scanned in the first implementation is used. A case where a series of processes are performed will be described. In this embodiment, a case where only one table exists in the document to be scanned will be described. The case where a plurality of tables exist will be described in the second embodiment described later.

First, the first implementation will be described.

In step S501, the scan instruction unit 421 instructs the display control unit 426 to display the scan setting screen. The display control unit 426 displays a scan setting screen for making various settings in the scan process on the operation unit 220.

FIG. 6 is a diagram showing an example of the scan setting screen 600. The scan setting screen 600 of FIG. 6 has five setting buttons 601 to 605. The [Color setting] button 601 is a button for setting color or monochrome when scanning a document. The [Resolution setting] button 602 is a button for setting the resolution when scanning the original. The [Double-sided scanning setting] button 603 is a setting button used when it is desired to scan both sides of a document. The [Document mixed loading setting] button 604 is a setting button used when it is desired to scan documents of different sizes at once. The [Image Format Setting] button 605 is a setting button used when designating the storage format of the scanned image data. At the time of setting using these setting buttons 601 to 605, candidates (candidate limbs) that can be set within the range supported by the MFP 110 are displayed, and the user selects a desired one from the displayed candidates. The above-mentioned setting button is an example, and all of these setting items may not exist, or setting items other than these may exist. The user also makes detailed settings for the scan process via such a scan setting screen 600. The [Cancel] button 620 is a button used when canceling the scan setting. The [scan start] button 621 is a button for instructing the start of the scan process for the document set on the platen or the like.

In step S502, the scan instruction unit 421 determines whether the [scan start] button 621 is pressed or the [cancel] button 620 is pressed. When it is determined that the [scan start] button 621 is pressed, the scan instruction unit 421 causes the scan execution unit 411 to perform a scan process by setting the setting items selected by the scan setting buttons 601 to 605. When it is determined that the [Cancel] button 620 is pressed, the process ends.

In step S503, the scan execution unit 411 issues a scan instruction to the scanner unit 222 and scans the document. The scanned image data generated by scanning is stored in the image data storage unit 412, and the corresponding scan image identifier is notified to the scan instruction unit 421.

In step S504, the scan instruction unit 421 acquires the scan image data corresponding to the scan image identifier from the image data storage unit 412.

In step S505, the metadata generation unit 422 sends an analysis instruction of the scanned image data acquired from the image data storage unit 412 to the image analysis unit 423. The image analysis unit 423 analyzes the scanned image data. For example, the layout in the scanned image such as the character string area and the table area is analyzed by extracting the histogram of the scanned image or extracting the pixel block. By this analysis, the character string area in the entire scanned image is extracted. The character string area is an area (image area) presumed to be a character string. The table area is an area (image area) presumed to be a table. The character string area also includes an area of one character. The layout analysis process may include a process of correcting the inclination of the scanned image so that the layout can be easily performed, or a process of detecting the direction and rotating the image. After that, by performing character recognition processing (OCR: Optical Character Recognition) processing on the character string area, characters (text data) included in the character string area (image area) are extracted. The character recognition process is a process of recognizing a character (text data) by, for example, matching a pixel group included in a character string area with a pre-registered dictionary. This character recognition process may take time. Therefore, in the present embodiment, the character recognition process is performed on the character string area desired by the user without sequentially performing the character recognition process on the character string area extracted by the layout analysis. We are trying to increase the speed. The information of the character string area analyzed by the image analysis unit 423 (hereinafter referred to as the character string area information) is passed to the metadata generation unit 422.

Here, the details of the image analysis process in step S505 will be described with reference to FIG. 7. FIG. 7 is a flowchart showing the details of the image analysis process (step S505) by the image analysis unit 423. Hereinafter, the flow will be described with reference to FIG.

In step S701, the image analysis unit 423 reads the scanned image data received from the file generation unit 425 in a form that can be analyzed.

In step S702, the image analysis unit 423 corrects the read scanned image data to a state in which subsequent area determination and character string analysis can be easily performed. Specifically, the scanned image data is corrected to a state where it is easy to perform analysis processing by binarizing the image signal, correcting the tilt of the original that is misaligned during scanning, and rotating the original in the upright direction. do.

In step S703, the image analysis unit 423 analyzes the content of the scanned image data corrected in step S702 to determine the character string area and the table area. For example, the image analysis unit 423 performs edge extraction or the like on the corrected scan image (binary image) to specify the character string area and the table area in the image. That is, a block (unit area) that is presumed to be a continuous character string and a block (unit area) that is presumed to be a table are specified. With respect to the character string area and the table area, the coordinates, the width direction (horizontal direction), and the height direction (vertical direction) are specified, respectively. The width direction (horizontal direction) of the character string area indicates a direction along the text direction of the document. The height direction (vertical direction) of the character string region indicates a direction that intersects with a direction along the text direction of the document, for example, a direction orthogonal to each other. Also, specify whether the text direction is horizontal or vertical in the manuscript. There is a method of taking vertical and horizontal projections on a scanned image (binary image) and determining the lower dispersion of the projections as the row direction, which can be used. Table 2 below shows an example of the result of performing image analysis processing on a part of the scanned image of a certain quotation.

In step S704, the image analysis unit 423 acquires similar form information from the form information holding unit 427 based on the character string area and the table area determined in step S703, and generates a file name in advance.

Here, the details of the file name list generation process in step S704 will be described with reference to FIG. FIG. 11 is a flowchart showing the details of the file name list generation process (step S704) by the image analysis unit 423.

In step S1101, the image analysis unit 423 determines whether the character string area acquired in step S703 is similar to the form information held in the form information holding unit 427. When the character string area of the scanned image data overlaps with the form information held in the form information holding unit 427 at a predetermined ratio or more, it is similar to the form information held in the form information holding unit 427. It is determined that there is similar form information, and the process proceeds to step S1102. On the other hand, if the character string area of the scanned image data overlaps less than a predetermined ratio with the form information held in the form information holding unit 427, it is determined that there is no similar form information, and this flow ends. In step S1101, a similarity determination is made for all the form information held in the form information holding unit 427. The predetermined ratio, which is the criterion for determining the similarity, is a numerical value that can be set and changed by the user. It is also possible to weight the similarity determination according to the region. In the first implementation, since the form information holding unit 427 does not hold any form information, the file name list generation process is completed. The processing after step S1102 will be described in the second implementation.

Table 2 shows an example of the character string area information analyzed by the layout analysis process.

In Table 2 above, [number] is a number uniquely indicating each specified character string area. In this example, serial numbers from 1 to 13 are assigned in the order of recognition. It is assumed that the coordinates have the X-axis in the right direction and the Y-axis in the downward direction with the upper left of the preview display area 810 described later as the origin (0,0). [X coordinate] of [Area] indicates the X coordinate of the upper left corner of each specified character string area. [Y coordinate] of [Area] indicates the Y coordinate of the upper left corner of each specified character string area. Hereinafter, when the term "coordinates" is used with respect to the character string area, it means the position coordinates of the upper left corner of the character string area unless otherwise specified. [Width] of [Area] indicates the distance from the left side to the right side of each specified character string area. [Height] of [Area] indicates the distance from the upper side to the lower side of each specified character string area. In the present embodiment, the [X coordinate], [Y coordinate], [width], and [height] are all indicated by pixels, but may be indicated by points, inches, or the like.

Return to the flowchart of FIG.

In step S506, the metadata generation unit 422 acquires each character string area information (image analysis data) analyzed by the image analysis unit 423 and extracted from the scanned image. The character string area information is, for example, acquired in a CSV or XML format, but may be acquired in another format. Further, it may be acquired at a predetermined timing after being temporarily stored in the HDD 214.

In step S507, the metadata generation unit 422 instructs the display control unit 426 to display the preview screen. The display control unit 426 displays a preview screen on the touch panel of the operation unit 220 using the scan image data received from the scan instruction unit 421. The user can set the file name of the scanned image data via the preview screen.

FIG. 8A is a diagram showing an example of a document to be scanned. FIG. 8B is a diagram showing an example of a preview screen when the document (original) shown in FIG. 8A is scanned, and FIG. 8C is a preview display area 810 described later. It is a figure which shows an example of the case where the scanned image displayed in is scrolled downward. The user executes the file name setting for transmission to the file server 120, which is executed by the upload execution unit 424 via the preview screen 800, via the plurality of buttons 802 to 803. The [File name list display] button 802 displays the file name selection list set in the file name input field 801. The file name selection list is displayed in the second and subsequent processes. When it is determined that the area information similar to the area information obtained in this image analysis is held in the form information holding unit 427, and the selection information is added to the similar area information, the file name is selected. A list is generated. The file name selection list is composed of file names extracted from the area information obtained in this image analysis based on the selection information of similar area information. That is, when the [File name list display] button 802 is pressed, a file name selection list consisting of all file names (hereinafter referred to as candidate file names) that can be selectable candidates by the user is displayed. File. Table 3 shows an example of a file name selection list. This example shows a case where the area information similar to the area information shown in Table 2 is held in the form information holding unit 427 and the selection information is added to the similar area information. The form information holding unit 427 is composed of character strings in the character string area corresponding to the number 1 (estimate) in Table 2, the number 3 (R12-3456) in Table 2, and the number 13 (Kawasaki Co., Ltd.) in Table 2. The scanned image data of the file name to be used is retained. Further, the form information holding unit 427 has a character string in the character string area corresponding to the number 1 (estimate) in Table 2, the number 3 (R12-3456) in Table 2, and the number 8 (Shinagawa Co., Ltd.) in Table 2. The scanned image data of the file name composed of is retained. In such a state, the file name list generation process is performed on the scanned image data including the character string area information shown in Table 2. As a result, a file name selection list composed of the candidate file name of "Quotation_R12-3456_Kawasaki Co., Ltd." and the candidate file name of "Quotation_R12-3456_Shinagawa Co., Ltd." is generated.

The candidate file name is composed of a format in which one or more items constituting the file name and a delimiter for each item are combined. The items constituting the file name are also related to the OCR processing contents described later.

The button 803 is a button for setting the format of the file name and the like. It should be noted that the above-mentioned types of various buttons and modes of display and selection of each character string area are merely examples, and the present invention is not limited to these. For example, there may be a button for modifying / changing the character string displayed in the file name input field 801 or for confirming the file name.

In the preview screen 800, in the preview display area 810 at the center of the screen, a plurality of buttons 811 to 814 for changing the display state are also displayed together with the scanned image. Buttons 811 and 812 are buttons that appear when the entire scanned image cannot be displayed, and are buttons for scrolling the display area in the vertical direction. The touch panel provided by the MFP 110 is usually not very large. Therefore, for example, when the scanned image is an A4 vertical / horizontal writing original, the entire width direction (short direction) of the scanned image is reduced and displayed in the preview display area 810. Is initially set. That is, in the initial setting, the lower part of the A4 vertical scanned image is not displayed in the preview display area 810. In such a case, when the "↓" button 812 is pressed, the display area scrolls down and the lower part can be displayed. Further, when the "↑" button 811 is pressed, the display area scrolls upward and the upper part can be displayed again.

Further, when the scanned image is, for example, A4 horizontal or A3, a button for scrolling the display area in the horizontal direction may be further provided. Buttons 813 and 814 are buttons for enlarging / reducing the display area, and when the "+" button 813 is pressed, the zoom-in is performed, and when the "-" button 814 is pressed, the zoom-out is performed. The operation by these button operations may be realized by the operation by the user's finger such as swipe or pinch out / pinch in on the preview screen. Further, in the preview display area 810, the character string area specified by the image analysis process of step S505 is in a mode that can be selected and identified by the user based on the above-mentioned character string area information (for example, a box). Is displayed. An arbitrary character string area is selected (for example, touched by a finger) from the character string area displayed in the preview display area 810 in a manner identifiable by the user. Along with this selection operation, the character string included therein is displayed in the file name input field 801, that is, is automatically input, and becomes a part of the character string constituting the file name. The [Back] button 830 is a button used when canceling the preview display. The [Next] button 831 is a button for moving to a screen for setting an upload destination of the read scanned image data.

The file name character string setting areas 815 to 827 are displayed in the preview display area 810 according to the character string area information obtained by the image analysis unit 423 analyzing the scanned image data. The character string area information indicates the position on the scanned image data as shown in Table 2. Therefore, the character string area information is displayed at a position where the scroll position and enlargement / reduction of the scanned image data displayed in the preview display area 810 are reflected. When this character string area is touched by the user, the character string in the character string area touched by the user is input to the file name input field 801. The area shown by the diagonal line indicates the area recognized as a character string and has a rectangular shape. The shaded area indicates the area that has already been touched by the user and selected as the file name. The setting items using each of the buttons 811 to 814 and the areas 815 to 827 may not have the setting items described here, or may have other setting items.

In step S508, the file generation unit 425 generates a file name for the scanned image based on an input instruction from the user.

Here, the details of the file name generation process in step S508 will be described with reference to FIG. FIG. 9 is a flowchart showing the details of the file name generation process (step S508). Hereinafter, the flow will be described with reference to FIG.

In step S901, the presence or absence of a touch operation by the user on the preview screen 800 displayed on the touch panel is monitored. When the touch operation is detected, the process proceeds to step S902. In the following step S902, the processing is separated according to the content of the touch operation. If the content of the touch operation detects that the button has been pressed, the process proceeds to step S911. In step S911, the process is separated according to the type of the pressed button. When it is detected that a button other than the [File name list display] button 802 is pressed, this flow ends, and when it is detected that the [File name list display] button 802 is pressed, the step is performed. Proceed to S912. The processing after step S912 will be described in the second implementation.

On the other hand, if it is detected that an operation other than pressing the button has been performed, the process proceeds to step S903.

In step S903, the position coordinates (x, y) on the touch panel on which the touch operation is performed are acquired. In the following step S904, it is determined whether or not the touch-operated position coordinates overlap with any character string area displayed in a manner selectable and identifiable by the user. For example, the touch-operated position coordinates are inside each character string area displayed in the preview display area 810 in a manner selectable and identifiable by the user (a rectangle specified by the position coordinates representing the four corners of the character string area). It is judged whether it is included in (inside). If the touch-operated position coordinates overlap with any of the character string areas displayed in a manner selectable and identifiable by the user, the process proceeds to step S905. On the other hand, if they do not overlap, the process returns to step S901.

In step S905, the character string in the character string area that overlaps with the touch-operated position coordinates is acquired. The character string is acquired by performing OCR processing on the character string area selected by the touch operation (hereinafter referred to as the selected character string area) in the image analysis unit 423 and extracting the character string. Then, in step S906, the file name currently displayed in the file name input field 801 is acquired. In the following step S907, it is determined whether the content of the acquired file name is "empty". Here, the file name "blank" means a blank state in which no character string is displayed in the file name input field 801. If the acquired file name is "empty", the process proceeds to step S909. On the other hand, if it is not "empty", the process proceeds to step S908.

In step S908, a process of adding a predetermined delimiter to the end of the file name acquired in step S906 is performed. As a predetermined delimiter, an underscore will be described here as an example, but the present invention is not limited thereto. For example, it may be a symbol / character other than an underscore such as a hyphen, or it may be a symbol / character without an entity such as a space.

In step S909, the character string (character string extracted from the selected character string area) acquired in step S905 is set as a component of the file name. At this time, if the already set character string exists, it is added to the end. Then, in step S910, the character string currently set is displayed (automatically input) in the file name input field 801. While the user is touching the character string area displayed on the preview screen, the above-mentioned processes of steps S901 to S910 are repeated.

The above is the content of the file name generation process. By such a process, a delimiter is inserted between a plurality of character string areas selected by the user, and a file name of the scanned image is generated.

FIG. 8B shows the state of the preview screen 800 after the file name is generated in step S508. In this example, the character string area corresponding to "Quotation", "R12-3456", and "Kawasaki Co., Ltd." is sequentially selected, so that the character string of "Quotation_R12-3456_Kawasaki Co., Ltd." is a file. It is displayed (set) in the name input field 801. In the preview display area 810, areas 815, 821, and 827 indicating the character string used for the file name by the user's touch operation are displayed in a rectangular shape. Then, when the desired file name is generated and the user presses the [Next] button 831, the flow ends through steps S901, S902, and S911.

Return to the flowchart of FIG.

In step S509, the metadata generation unit 422 divides the processing according to the content of the button operation by the user. When the press of the [Next] button 831 is detected, the information of the file name (character string set as the file name) displayed in the file name input field 801 is sent to the upload execution unit 424, and the process proceeds to step S510. move on. When the pressing of the [Back] button 830 is detected, the process returns to step S501 (display of the scan setting screen). If an operation other than the [Next] button 831 and the [Back] button 830 is detected, the process returns to step S508 (file name generation).

In step S510, the metadata generation unit 422 acquires the file name set in the file name input field 801. The metadata generation unit 422 passes the acquired file name and the scanned image identifier to the upload execution unit 424.

In step S511, the upload execution unit 424 instructs the display control unit 426 to display a UI screen (hereinafter, referred to as an upload setting screen) for setting a transmission destination of the scanned image data. The display control unit 426 displays an upload setting screen for making various settings in the data transmission process on the operation unit 220. The user makes detailed settings related to uploading to the file server 120 via the upload setting screen.

FIG. 10 is a diagram showing an example of the upload setting screen 1000. The user inputs the folder path for transmission to the file server 120 in the [folder path] input field 1001. In the example of FIG. 10, "\\ Server1 \ Share \ ScanData" is input as the folder path. As a method of inputting the folder path, for example, a sub-window (not shown) of the keyboard screen is displayed in response to a tap operation to the [folder path] input field 1001, and the user inputs the path name via the keyboard screen. It may be possible to set it. Alternatively, an address book reference screen (not shown) may be displayed so that the user can select an address from the address book data stored in the HDD 214 of the MFP 110. The [Back] button 1020 is a button used when canceling the detailed setting related to uploading. The [Upload] button 1021 is a button for instructing uploading to the folder path set in the [Folder path] input field 1001.

In step S512, the upload execution unit 424 divides the process according to the content of the button operation by the user, as in step S509. If the pressing of the [Upload] button 1021 is detected, the process proceeds to step S513. On the other hand, when the pressing of the [Back] button 1020 is detected, the process returns to step S507 (display of the preview screen).

In step S513, the upload execution unit 424 acquires the file server setting, passes the file server setting, the folder path acquired in step S511, and the file name acquired in step S510 to the metadata generation unit 422. At that time, the path name input in the [folder path] input field 1001, the file name generated in step S508, and the file server setting are information necessary for storing the scanned image data in the file server 120. For example, it contains information such as a host name, a folder path origin, a user name and password for login.

In step S514, the metadata generation unit 422 generates a storage destination path for the scanned image data based on the information received from the upload execution unit 424. For example, it is generated by adding the folder path to the file server settings (host name of the file server 120, starting point of the folder path). As a result, a storage destination path such as "\\ Server01 \ Share \ ScanData" is generated.

In step S515, the upload execution unit 424 executes access to the file server 120. At this time, the user name and password included in the file server settings are transmitted to the file server 120. The file server 120 that has received the user name and password executes the authentication process.

In step S516, the upload execution unit 424 divides the processing according to the authentication result in the file server 120. That is, when the notification of the authentication success is received from the file server 120, the process proceeds to step S517. On the other hand, when the notification of authentication failure is received, this process is terminated.

In step S517, the upload execution unit 424 transmits the scanned image data to the folder indicated by the storage destination path generated in step S514, and stores the scanned image data in the file server 120.

In step S518, the image analysis unit 423 holds the character string area information acquired in step S506 and the character string area information (selection information) acquired and selected in step S508 in the form information holding unit 427.

Table 4 shows an example of the retained character string area information and the selected character string area information.

The form number is a number uniquely assigned to each form information held in the form information holding unit 427. Here, it is 1 because it is the first type of form. Further, the form information holding unit 427 holds the selection information. The number of the selection information represents the order of the character string area selected by the user in the process of step S508.

The above is the content of the overall control up to the storage of the character string area information. In this embodiment, it is assumed that the processes of steps S503 to S508 are performed on the scanned image data for one page generated by executing the scan process. For example, a button for performing image analysis of the next page is provided in the preview display area 810, the preview display of the next page obtained by the analysis is performed, and the file name is configured from the character string area of the next page and subsequent pages. You may be able to set a character string.

Next, the second implementation will be described. In the second implementation, a description will be given using a document of FIG. 12 (a) similar to the document shown in FIG. 8 (a) and a scanned image displayed in the preview display area 1210 in FIG. 12 (b). do. That is, it is assumed that the new scan image data obtained in the second scan process is data that is determined to be similar to the past scan image data. The new scanned image data is different from the past scanned image data in the size of the table and the position of the character string region existing in the vicinity of the table. Further, it is assumed that the information set in the past scanned image data is set based on the characters in the character string area existing in the vicinity of the table of the past scanned image data.

The difference from the first implementation is that the processing of steps S1102 to S1114 shown in FIG. 11 and the processing of steps S912 to S914 shown in FIG. 9 are performed. The description of the same processing as that of the first implementation will be omitted as appropriate. Further, in the second execution, it is premised that the scan process and the processes of steps S501 to S505 and steps S701 to S703 have already been executed. Further, the form information holding unit 427 inputs the scanned image shown in the preview display area 810 in FIGS. 8B and 8C into the file name input field 801 "Quotation_R12-3456_Kawasaki Co., Ltd." It is assumed that the file name is retained.

Table 5 shows an example of a character string region obtained by scanning the document shown in FIG. 12A and analyzing the content of the image data corrected in step S702 by the image analysis unit 423 in step S703. Shows. The table indicated by the number 10 corresponds to the table 1224 shown in FIG. 12 (b), and is larger in the height direction of the region by one more row than the table obtained in the first implementation. ing.

In step S1101, the image analysis unit 423 determines that the form information similar to the scanned image data stored in the image data storage unit 412 is held in the form information holding unit 427 and that there is similar form information. Based on the determination result that there is similar form information, the process proceeds to step S1102.

In step S1102, the image analysis unit 423 has one target form among the form information stored in the form information holding unit 427 that is similar to the scanned image data stored in the image data storage unit 412. Identify the information.

In step S1103, the image analysis unit 423 acquires all the selected character string areas from the target form information specified in step S1102.

In step S1104, the image analysis unit 423 identifies one target selected character string area from all the selected character string areas acquired in step S1103.

In step S1105, the image analysis unit 423 determines whether or not there is a table (exists or does not exist) on the selected character string region of the target specified in step S1104 in the coordinate system (x, y). judge. If the image analysis unit 423 determines that the table is above the target selected character string area, the process proceeds to step S1106. On the other hand, if the image analysis unit 423 determines that there is no table on the target selected character string area, the process proceeds to step S1108.

Here, a procedure for determining whether or not there is a "table" on the target selected character string area in the coordinate system (x, y) will be described using the character string area information shown in Table 4. Since the origin (0,0) is the upper left of the document as the coordinates of the area, it is judged that the smaller number is on the upper side. For example, the relationship between the "table" and the "quotation", "R12-3456" and "Kawasaki Co., Ltd." will be described.

The "estimate" corresponds to number 1 in Table 4, and since the Y coordinate of the area is 24 and the height of the area is 30, it exists at the position coordinates of 24 to 54 in the Y coordinate. become. On the other hand, the "table" corresponds to the number 10 in Table 4, and since the Y coordinate of the area is 190 and the height of the area is 120, it exists in the range of 190 to 310 in the Y coordinate. Will be done. Comparing the position coordinates of the "estimate" and the "table", the position coordinates of the "estimate" are smaller than the position coordinates of the "table". It is judged that there is no.

"R12-3456" corresponds to the number 3 in Table 4, and since the Y coordinate of the area is 99 and the height of the area is 22, it exists in the range of 99 to 121 in the Y coordinate. become. Comparing the position coordinates of "R12-3456" and "table", since the position coordinates of "R12-3456" are smaller than the position coordinates of "table", the number 3 (R12) is the same as the number 1 (estimate). It is determined that there is no number 10 (table) above -3456).

"Kawasaki Co., Ltd." corresponds to number 13 in Table 4, and since the Y coordinate of the area is 359 and the height of the area is 30, it exists in the range of 359 to 389 in the Y coordinate. become. Comparing the position coordinates of "Kawasaki Co., Ltd." and "Table", the position coordinates of No. 13 (Kawasaki Co., Ltd.) are larger than the position coordinates of No. 10 (Table). Is determined to have number 10 (table). When the image analysis unit 423 determines that the table is above the selected character string area, the image analysis unit 423 proceeds to step S1106 and derives the distance from the table in step S1106. On the other hand, if the image analysis unit 423 determines that there is no table on the selected character string area, the process proceeds to step S1108, and the file name used character string area is specified in step S1108.

In step S1106, the image analysis unit 423 derives the distance between the target selected character string area and the table. In the example, the table of number 10 exists in the range of 190 to 310 in the Y coordinate, and the selected character string area of the number 13 exists in the range of 359 to 389 in the Y coordinate, so that the table of number 10 and the number 13 exist. The distance of the selected character string area (Kawasaki Co., Ltd.) is 49 (= 359-310).

In step S1107, the selected character string area to be used as the file name in the scanned image data is specified based on the distance derived in step S1106, the selected character string area of the target specified in step S1104, and the scan image data table. To. That is, the character string area used for the file name is specified. As a result, the relationship between the position coordinates of the table and the character string area to which the selection information is attached in the past scan image data determined to be similar to the new scan image data in the new scan image data is similar. The selected string area that exists or has the same relationship is identified. In this embodiment, based on the distance between the character string areas of No. 13 and No. 10 in Table 4, the position coordinates of the selected character string area of No. 13 in Table 4, and the character string area (table) of No. 10 in Table 5. The corresponding character string area is specified in Table 5. It has the same X coordinate (236) and height direction size (30) as the number 13 in Table 4, and is located at a distance (49) from the Y coordinate 340 (= 190 + 150) at the lower end of the number 10 (table) in Table 5. The character string area of the number 13 in Table 5 in (389) corresponds to this. If the character string area at the same position as the selected character string area at the bottom of the table of similar past scanned image data is extracted from the scanned image data without using the above distance, the character string area of number 12 in Table 5 is extracted. Will be applicable and a character string not intended by the user will be extracted.

In step S1108, the image analysis unit 423 specifies the corresponding character string area among the character string areas of the scanned image data as the file name used character string area based on the target selected character string area. That is, the image analysis unit 423 holds the selected character string area specified in step S1104 in the storage area of the RAM 213.

In step S1109, the image analysis unit 423 determines whether or not all the selected character string areas have been processed. If there is an unprocessed selected character string area and the image analysis unit 423 determines that all the selected character string areas have not been processed, the process returns to step S1104 and the processes of steps S1104 to S1108 are performed. If it is determined that the image analysis unit 423 has processed all the selected character string areas, the process proceeds to step S1110.

By the process up to step S1109, the target area is detected based on the form information of the specified target, the table included in the past scanned image data determined to be similar, and the table included in the new scanned image data. The target area is an area to be processed in the character string area extracted from the new scanned image data.

In step S1110, the image analysis unit 423 performs OCR processing on the selected character string area held in the storage area of the RAM 213, which is the target area, obtains the character string of the file name used character string area, and obtains the file. Generate a name. The file name is generated by acquiring the character strings in the file name used character string area in the same order as the selection information of the past scanned image data.

In step S1111, the image analysis unit 423 determines whether the file name selection list held in the storage area of the RAM 213 overlaps with the file name generated in step S1110. If it is determined that the image analysis unit 423 is duplicated, the process proceeds to step S1112, and in step S1112, the image analysis unit 423 moves the duplicated file name to the top of the file name selection list. On the other hand, when it is determined that the image analysis unit 423 does not overlap, the process proceeds to step S1113, and in step S1113, the image analysis unit 423 holds the file name generated in step S1110 in the storage area of the RAM 213. Add to the name selection list.

In the present embodiment, the character string extracted by image processing is used as information to be added to the folder name or file name of the image data storage destination, but it can also be used for other purposes. For example, it is possible to specify a telephone number corresponding to a character string and fax the image data to the telephone number, or specify an email address and send an email.

Further, in the above, the method of specifying the file name selection character string area based on the distance between the table and the selection character string area at the bottom of the table has been described. It is also possible to specify the file name selection character string area based on the quantity of the character string area between the table and the selection character string area at the bottom of the table instead of the distance.

Further, in the above, the case where the file name selection character string area is outside the table in the coordinate system (x, y) has been described. When the file name selection character string area is in the table in the coordinate system (x, y), it is also possible to specify the file name selection character string area from the item position in the table instead of the coordinate position. be.

Here, in the flow of FIG. 9 showing the details of the file name generation process S508, the difference from the first implementation will be described. Specifically, a case where a candidate file name is selected as a file name from the file name selection list displayed by pressing the "File name list display" button will be described. It is premised that the form information holding unit 427 holds the form information similar to the scanned image data obtained in the second implementation.

In step S911, the process is separated according to the type of the pressed button. When it is detected that the [File name list display] button 802 is pressed, the process proceeds to step S912. In step S912, the display control unit 426 displays the candidate file names created based on the form information determined to be similar by the image analysis unit 423 as a file name selection list. If the form information holding unit does not hold the form information similar to the scanned image data, the file name selection list is not displayed even if the "file name list display" button 802 is pressed. As a method of displaying the file name selection list, for example, a method of displaying a list of options of a plurality of candidate file names by pulling down may be mentioned. Further, among the files held in the form information holding unit 427, the candidate file names most similar to the scanned image data are moved to the beginning of a plurality of candidate file names displayed in the pull-down menu, and further highlighted. It is possible. For example, as shown in FIG. 16, the file name selection list 1601 including the area 1602 for displaying the most similar candidate file names with diagonal lines and the area 1603 for displaying other candidate file names without decoration is pulled down. The method of displaying with is mentioned. In addition, there is a method of displaying only the target candidate file name in a large font or bold or red as compared with other candidate file names.

In step S913, it is determined whether the candidate file name is selected by the user from the file name selection list. If the selection of the candidate file name is detected, the process proceeds to step S914. On the other hand, if the selection of the candidate file name is not detected, this flow ends.

In step S914, the character string of the candidate file name that overlaps with the touch-operated position coordinates is acquired. Then, the process proceeds to step S910, and in step S910, the character string currently set is displayed (automatically input) in the file name input field 801.

In this way, the candidate file name is generated by using the character string area information selected as the file name of the similar scan image data among the past scan image data. Therefore, it is possible to save the trouble of selecting a character string on the preview screen. Even if the position of the description item is not determined in advance and the format is the same, the description field can be expanded and the position of the description item changes according to the size of the document. The area where OCR processing is performed can be appropriately specified, and this information can be reliably acquired. As a result, the file name can be easily set for similar scanned image data according to the same rule.

[Embodiment 2]
Next, the second embodiment of the present invention will be described. In the first embodiment, the case of processing a document in which one table is described will be described, but in the present embodiment, the case of processing a document in which two or more tables are described will be described. The difference between the present embodiment and the first embodiment is a process of deriving the distance between the table and the character string region (step S1106), and a preview screen. The details of the process of step S1106 will be described with reference to the flowcharts shown in FIGS. 13 and 14. The difference between the flowchart shown in FIGS. 13 and 14 and the flowchart shown in FIG. 11 is that the processes of steps S1301 to S1306 are performed. Further, the preview screen will be described with reference to the preview screen shown in FIG. As for the other configurations, which are the same as those in the first embodiment, the description thereof will be omitted as appropriate. In this embodiment, it is assumed that the form information holding unit 427 stores the information in the character string area as shown in Table 6.

Table 7 shows an example of a character string region obtained by scanning the document shown in FIG. 15A and analyzing the content of the image data corrected in step S702 by the image analysis unit 423 in step S703. Shows. The table represented by number 10 corresponds to table 1425 shown in FIG. 15 (b), and the table represented by number 11 corresponds to table 1424 shown in FIG. 15 (b).

FIG. 14 is a flowchart showing the details of the distance derivation process in step S1301 in FIG. Hereinafter, the flow will be described with reference to FIG.

In step S1302, the image analysis unit 423 acquires all tablespace information from the target form information. In the example shown in Table 6, the tablespace information corresponding to each of the number 10 and the number 11 is acquired. Each tablespace information includes the X and Y coordinates of the tablespace and the width and height directions of the tablespace. With respect to the table corresponding to the number 10, the tablespace information in which the X-coordinate and the Y-coordinate of the area are 37 and 190 and the sizes in the width direction and the height direction are 110 and 120 are acquired. For the table corresponding to number 11, obtain tablespace information in which the X and Y coordinates of the area are 157 and 190 and the sizes in the width and height directions are 360 and 120.

In step S1303, the image analysis unit 423 identifies one target tablespace. In the example shown in Table 6, the table corresponding to the number 10 or the number 11 is specified.

In step S1304, the image analysis unit 423 derives the distance between the selected character string area of the target specified in step S1104 and the table area of the target specified in step S1303. Here, a case where the selected character string area corresponding to the number 14 is specified in step S1104 and the table area corresponding to the number 10 is specified in step S1303 will be described. The selected character string area of the number 14 is in the range of 359 to 389 in the Y coordinate, and the table area of the number 10 is in the range of 190 to 310 in the Y coordinate. Therefore, the distance in the Y-axis direction is 49 (= 359-310). Further, regarding the X coordinate, the selection character string area of the number 14 is 236, the table area of the number 10 is 37, and therefore the distance in the X-axis direction is 199 (= 236-37).

In step S1305, the image analysis unit 423 determines whether or not all the table areas have been processed by the target form information. If there is an unprocessed table area and the image analysis unit 423 determines that all the table areas have not been processed, the process returns to step S1303 and the processes of steps S1303 to S1305 are performed. If it is determined that the image analysis unit 423 has processed all the tablespaces, the process proceeds to step S1306.

In step S1306, the image analysis unit 423 specifies the table with the shortest distance derived in step S1304, that is, the table closest to the selected character string region , as the table to be derived from the distance. In the example shown in Table 6, the distance between the selected character string area of No. 14 and the table area of No. 10 derived in step S1304, and the selected character string area of No. 14 and the number 11 derived in step S1304. Is compared to the distance to the tablespace. The distance between the selected character string area of number 14 and the table of number 10 is 199 in the X-axis direction and 49 in the Y-axis direction. On the other hand, the distance between the selected character string area of No. 14 and the table of No. 11 is 79 in the X-axis direction and 49 in the Y-axis direction. Comparing the distances between the table of No. 10 and the table of No. 11, the distances are the same in the Y-axis direction, and in the X-axis direction, the distance of the table of No. 11 is compared with that of the table of No. 10. The distance is shorter. Therefore, instead of the table of the number 10, the table of the number 11 is specified as the table of the distance derivation target. As a result, the table specified in step S1306 is used when specifying the file name used character string area in step S1107.

As described above, even when a plurality of description columns such as a table are included, OCR processing is performed on the scanned image data of the document in which the position of the description item changes according to the size of the description column, as in the first embodiment. It is possible to properly identify the area to be performed and surely obtain this information. As a result, the file name can be easily set for similar scanned image data according to the same rule.

[Other embodiments]
The present invention supplies a program that realizes one or more functions of the above-described embodiment to a system or device via a network or storage medium, and one or more processors in the computer of the system or device reads and executes the program. It can also be realized by the processing to be performed. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

110 MFP
421 Scan instruction unit 422 Metadata generation unit 423 Image analysis unit 425 File generation unit 426 Display control unit 427 Form information retention unit

Claims (14)

A device for setting information in scanned image data obtained by scanning a document containing a table.
An extraction means for extracting area information about each of the character string area and the table area, which are presumed to be a character string and a table, in the new scanned image data.
The area information extracted in the new scan image data by the extraction means is compared with the area information extracted in each of the past scan image data, whereby the area information extracted in the new scan image data is described. Judgment means for determining past scanned image data from which area information similar to area information has been extracted , and
The determination that the character string region used when setting information for the past scanned image data determined by the determination means that the similar region information has been extracted and the similar region information have been extracted. Based on the distance between the table area extracted from the past scanned image data determined by the means and the target area to be processed among the character string areas extracted from the new scanned image data. The detection means to detect and
A recognition means that performs character recognition processing in the target area, and
A device characterized by having as a setting means for setting information in the new scanned image data using characters obtained as a result of the character recognition process. The detection means has the size of the table area and the character string area existing in the vicinity of the table area in the new scan image data and the past scan image data for which it is determined that the similar area information has been extracted. The information set in the past scan image data for which the position of the similar region information is different and the similar region information is determined to be extracted is the past scan image data for which the similar region information is determined to be extracted . When the data is set based on the characters in the character string area existing in the vicinity of the table area , it is determined that the character string areas existing in the vicinity of the table area of the new scanned image data are similar to each other. To detect the character string area corresponding to the relationship between the table area in the past scanned image data and the character string area used when obtaining the information set for the past scanned image data as the target area. The apparatus according to claim 1. It has an acquisition means for acquiring the position coordinates of the table area and the character string area of the new scanned image data.
Based on the position coordinates of the acquired table area and the character string area, the detection means extracts the similar area information from the character string areas existing in the vicinity of the table area of the new scanned image data. The character string area corresponding to the relationship between the table area in the past scanned image data determined to be and the character string area used to obtain the information set for the past scanned image data is detected as the target area. The device according to claim 2, wherein the device is to be used. The detection means is a character string existing in the vicinity of the table area of the new scanned image data when the position coordinates of the acquired character string area are lower than the position coordinates of the acquired table area . Of the areas, the table area in the past scanned image data for which it is determined that the similar area information has been extracted and the character string area used for obtaining the information set for the past scanned image data. The apparatus according to claim 3, wherein the character string area corresponding to the relationship is detected as the target area. The detection means determines that, among the character string regions existing in the vicinity of the table area of the new scanned image data, the distance from the table area of the new scanned image data is similar to the area information extracted. The target area is a character string area having position coordinates that are the same as the distance between the table area in the past scanned image data and the character string area used to obtain the information set for the past scanned image data. The apparatus according to claim 4, wherein the device is detected as. The apparatus according to any one of claims 1 to 5, further comprising a display control means for displaying the target area on the display means together with the scan image of the new scan image data. The device according to claim 6, wherein the display control means displays the information on the display means. If there is more than one of the above information
The apparatus according to claim 7, wherein the display control means highlights the information generated corresponding to the past scan image data determined to be most similar to the new scan image data. The display control means moves the information generated corresponding to the past scan image data determined to be most similar to the new scan image data to the top of the list displaying the plurality of information. The device according to claim 8, wherein the device is displayed. The document comprises a plurality of the tablespaces .
The target area according to claim 1 to 9, wherein the detection means detects the target area based on the table area closest to the character string area existing in the vicinity of the table area among the plurality of table areas . The device according to any one item. The apparatus according to any one of claims 1 to 10, further comprising a holding means for holding the past scanned image data. The document is a form
The apparatus according to any one of claims 1 to 11, wherein the information is a file name given to the scanned image data. It is a method for setting information in the scanned image data obtained by scanning a document containing a table.
An extraction step that extracts area information about each of the character string area and the table area that are presumed to be a character string and a table in the new scanned image data, and
By comparing the area information extracted in the new scanned image data in the extraction step with the area information extracted in each of the past scanned image data, the area information was extracted in the new scanned image data. A determination step for determining past scanned image data from which region information similar to the region information has been extracted , and
The determination that the character string region used when setting information for the past scanned image data determined in the determination step that the similar region information has been extracted and the similar region information have been extracted. Based on the distance between the table area extracted from the past scanned image data determined in the step and the target area to be processed among the character string areas extracted from the new scanned image data. Steps to detect and
The step of performing character recognition processing in the target area and
A method comprising: a step of setting information in the new scanned image data using characters obtained as a result of the character recognition process. A program for making a computer function as each means of the apparatus according to any one of claims 1 to 12.

Images